Back to MCP Directory
Vectorize
Model Context Protocol moderate risk

Vectorize

The Vectorize MCP server enables vector search, text extraction, and deep research using the Vectorize.io platform, requiring API keys and pipeline IDs for operation.

Connections & Capabilities

Connects To

GitHubTwitter

Capabilities

readwriteexec

Quickstart

Install

npm install
npm run dev

Config

{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "org_id",
        "description": "Vectorize Organization ID"
      },
      {
        "type": "promptString",
        "id": "token",
        "description": "Vectorize Token",
        "password": true
      },
      {
        "type": "promptString",
        "id": "pipeline_id",
        "description": "Vectorize Pipeline ID"
      }
    ],
    "servers": {
      "vectorize": {
        "command": "npx",
        "args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],
        "env": {
          "VECTORIZE_ORG_ID": "${input:org_id}",
          "VECTORIZE_TOKEN": "${input:token}",
          "VECTORIZE_PIPELINE_ID": "${input:pipeline_id}"
        }
      }
    }
  }
}

Exposed MCP Tools (3)

safe
retrieve

Performs vector search and retrieves documents based on a given question.

Read-only operation; retrieves existing data based on a query.

moderate
extract

Extracts text from a document and chunks it into Markdown format.

Processes user-provided documents; potential for denial-of-service if large or malformed documents are submitted.

moderate
deep-research

Generates a private deep research report from your pipeline based on a query.

Performs web searches and generates reports; potential for information leakage or unintended data exposure.

Safety Assessment

This server's safety depends heavily on the security of the Vectorize API keys and the configuration of the Vectorize pipeline. It is relatively safe for read-only operations, but write operations and deep research carry moderate risks due to potential data exposure and dependency on external services.

  • Requires authentication via API key and Organization ID.
  • No direct filesystem access.
  • Limited to Vectorize.io API capabilities.
  • Can be configured with read-only access.
  • Exposes Vectorize API keys which, if compromised, could lead to unauthorized usage.
  • Potential for data exfiltration if the Vectorize pipeline is misconfigured.
  • Server executes commands via `npx`, which introduces a dependency on the npm ecosystem.
  • Deep Research tool can perform web searches, potentially leading to unintended data exposure.